# GPT-5.2 Codex vs Step 3

> GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 40.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-step-3
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5.2 Codex leads 45.5 to 40.1.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Codex | Step 3 |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 42.6 | 40.5 |
| Rank | 111 | 149 |
| Context | 400K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Codex: 45.5 (#71)
- Step 3: 40.1 (#147)

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1367 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 41.0 (#22)
- Step 3: —

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| Terminal-Bench | 66.5% | — |

## Reasoning

- GPT-5.2 Codex: —
- Step 3: 28.4 (#105)

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| LMArena Hard Prompts | — | 1355 |

## Math

- GPT-5.2 Codex: —
- Step 3: 37.6 (#148)

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |

## Knowledge

- GPT-5.2 Codex: —
- Step 3: 36.8 (#164)

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |

## Multimodal

- GPT-5.2 Codex: —
- Step 3: 35.5 (#86)

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- GPT-5.2 Codex: —
- Step 3: 46.3 (#159)

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |

## Instruction Following

- GPT-5.2 Codex: —
- Step 3: 70.4 (#164)

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |

## Long Context

- GPT-5.2 Codex: —
- Step 3: 40.3 (#157)

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |

## Writing & Preference

- GPT-5.2 Codex: —
- Step 3: 54.3 (#151)

| Benchmark | GPT-5.2 Codex | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| LMArena Multi-Turn | — | 1341 |

## FAQ

### Is GPT-5.2 Codex better than Step 3?

GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 40.5 on the Noometry Index.

### Is GPT-5.2 Codex or Step 3 better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 40.1 in the Noometry coding category.

### How many benchmarks do GPT-5.2 Codex and Step 3 share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Step 3 has 17.